I know about the Soundex and Double-Methaphone algorithms for “sounds-like” stringmatching in English. Where can I find a similar algorithm, or a port of one of the algorithms for the Dutch Language?
I know about the Soundex and Double-Methaphone algorithms for sounds-like stringmatching in English. Where
Share
If you’re only after the algorithm, I would check nltk out. If you supply the data, you might be able to test some with the FSTs (Finite State Transducers) contrib by Edward Loper and Steven Bird. Or perhaps use data from the “Alpino Dutch Treebank”, which is distributed along with nltk.